Výsledky vyhledávání - "Tompkins, Daniel P."

Report

Laugh Now Cry Later: Controlling Time-Varying Emotional States of Flow-Matching-Based Zero-Shot Text-to-Speech

Autor: Wu, Haibin, Wang, Xiaofei, Eskimez, Sefik Emre, Thakker, Manthan, Tompkins, Daniel, Tsai, Chung-Hsien, Li, Canrun, Xiao, Zhen, Zhao, Sheng, Li, Jinyu, Kanda, Naoyuki

People change their tones of voice, often accompanied by nonverbal vocalizations (NVs) such as laughter and cries, to convey rich emotions. However, most text-to-speech (TTS) systems lack the capability to generate speech with rich emotions, includin

Externí odkaz: http://arxiv.org/abs/2407.12229

Zobrazit plný text záznamu

Report

BEATs: Audio Pre-Training with Acoustic Tokenizers

Autor: Chen, Sanyuan, Wu, Yu, Wang, Chengyi, Liu, Shujie, Tompkins, Daniel, Chen, Zhuo, Wei, Furu

The massive growth of self-supervised learning (SSL) has been witnessed in language, vision, speech, and audio domains over the past few years. While discrete label prediction is widely adopted for other modalities, the state-of-the-art audio SSL mod

Externí odkaz: http://arxiv.org/abs/2212.09058

Zobrazit plný text záznamu

Report

Maximizing Audio Event Detection Model Performance on Small Datasets Through Knowledge Transfer, Data Augmentation, And Pretraining: An Ablation Study

Autor: Tompkins, Daniel, Kumar, Kshitiz, Wu, Jian

An Xception model reaches state-of-the-art (SOTA) accuracy on the ESC-50 dataset for audio event detection through knowledge transfer from ImageNet weights, pretraining on AudioSet, and an on-the-fly data augmentation pipeline. This paper presents an

Externí odkaz: http://arxiv.org/abs/2202.03514

Zobrazit plný text záznamu

Report

COVID-19 Detection Using Recorded Coughs in the 2021 DiCOVA Challenge

Autor: Elizalde, Benjamin, Tompkins, Daniel

COVID-19 has resulted in over 100 million infections and caused worldwide lock downs due to its high transmission rate and limited testing options. Current diagnostic tests can be expensive, limited in availability, time-intensive and require risky i

Externí odkaz: http://arxiv.org/abs/2105.10619

Zobrazit plný text záznamu

Report

Multi-label Sound Event Retrieval Using a Deep Learning-based Siamese Structure with a Pairwise Presence Matrix

Autor: Fan, Jianyu, Nichols, Eric, Tompkins, Daniel, Mendez, Ana Elisa Mendez, Elizalde, Benjamin, Pasquier, Philippe

Realistic recordings of soundscapes often have multiple sound events co-occurring, such as car horns, engine and human voices. Sound event retrieval is a type of content-based search aiming at finding audio samples, similar to an audio query based on

Externí odkaz: http://arxiv.org/abs/2002.09026

Zobrazit plný text záznamu